CtrlK
BlogDocsLog inGet started
Tessl Logo

miro-code-review

Use when the user wants to create a visual code review on a Miro board from a pull/merge request (GitHub, GitLab, or any forge), local uncommitted changes, or a branch comparison — produces a file-changes table, summary/architecture/security docs, and architecture diagrams, then links them back from the PR/MR.

93

1.39x
Quality

92%

Does it follow best practices?

Impact

96%

1.39x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered, actionable workflow skill with strong sequencing, explicit validation/feedback loops for the destructive PR-description edit, and clean progressive disclosure across verified reference files. The only demerits are minor redundancy of the triage principle and deferral of Miro MCP specifics to live schemas.

Suggestions

State the 'every artifact must earn its place' / value-gate principle once (in §4.5) and have §5 reference it instead of restating it, to trim redundancy.

Tighten the prose framing the Scaling Guidelines and Diagram Selection tables into one-line captions so the tables carry the detail.

Where Miro creation is deferred to 'per their schemas', add one minimal concrete example invocation per artifact type (table, document, diagram) to close the executability gap.

DimensionReasoningScore

Conciseness

The body is dense and actionable without explaining basics Claude already knows, but the 'every artifact must earn its place' principle is restated across §4.5 and §5 and some prose around the scaling/diagram tables could be tightened slightly. It sits clearly above the midpoint but not fully lean.

4 / 5

Actionability

It provides copy-paste-ready commands for GitHub, GitLab, REST fallback, local, and branch sources plus concrete link/diagram conventions, but Miro creation steps defer to 'the table tool's live schema' / 'per their schemas', leaving minor gaps in full executability.

4 / 5

Workflow Clarity

A clearly numbered §1→§6 workflow with explicit validation checkpoints: the §4.5 bail-out and per-artifact value gates decide before creating, the plan is announced in chat, and the outward-facing PR/MR edit has idempotency markers, replace-in-place rules, and a permission-failure → comment fallback.

5 / 5

Progressive Disclosure

The body is an overview that defers detail to seven real, one-level-deep reference files (verified to exist), each inline-signaled ('See references/source-links.md for ...') and summarized in a closing References section, with no nested reference chains.

5 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-formed description: concrete deliverables, explicit 'Use when' trigger covering all source types, third-person voice, and a distinctive niche. It earns top marks across all dimensions without fluff or over-claims.

DimensionReasoningScore

Specificity

The description lists multiple concrete deliverables — 'a file-changes table, summary/architecture/security docs, and architecture diagrams, then links them back from the PR/MR' — giving comprehensive, specific coverage of what the skill produces rather than vague abstractions.

5 / 5

Completeness

It explicitly answers both when ('Use when the user wants to create a visual code review on a Miro board from a pull/merge request ... local uncommitted changes, or a branch comparison') and what ('produces a file-changes table, summary/architecture/security docs, and architecture diagrams, then links them back').

5 / 5

Trigger Term Quality

It uses natural terms a user would say ('visual code review', 'Miro board', 'pull/merge request', 'local uncommitted changes', 'branch comparison') and includes synonyms ('pull/merge request', 'GitHub, GitLab, or any forge') for broad coverage.

5 / 5

Distinctiveness Conflict Risk

The niche is narrow and distinctive — generating a visual code review on a Miro board from PR/MR/local/branch sources — with triggers unlikely to fire for any other skill.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
miroapp/miro-ai
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.